add step

.gitattributes

@@ -0,0 +1 @@
+*.blend filter=lfs diff=lfs merge=lfs -text

rlcube/.gitignore

@@ -0,0 +1,219 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# Blender
+*.blend1

rlcube/cube.blend

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f68bff72e62e0e3a2edb7dabde52cfcaaeb20ddd1c14da298583b9c685f311
+size 1963196

rlcube/main.py

@@ -1,5 +1,7 @@
+from rlcube.cube2 import train
+
 def main():
-    print("Hello from rlcube!")
+    train()
 
 
 if __name__ == "__main__":

rlcube/pyproject.toml

@@ -1,10 +1,11 @@
 [project]
 name = "rlcube"
 version = "0.1.0"
-description = "Add your description here"
+description = "Reinforcement Learning for Rubik's Cube"
 readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
     "gymnasium>=1.2.0",
+    "numpy>=2.3.2",
     "stable-baselines3>=2.7.0",
 ]

rlcube/rlcube/cube2.py

@@ -0,0 +1,16 @@
+from .envs.cube2 import Cube2
+
+def train():
+    env = Cube2()
+
+    obs, _ = env.reset()
+    for i in range(4):
+        # action = env.action_space.sample()
+        obs, reward, terminated, truncated, _ = env.step(0)
+        obs, reward, terminated, truncated, _ = env.step(1)
+        print(obs)
+        print("--------------------------------")
+        if terminated or truncated:
+            break
+
+    env.close()

rlcube/rlcube/envs/cube2.py

@@ -0,0 +1,62 @@
+import gymnasium as gym
+import numpy as np
+
+FRONT = 0
+RIGHT = 1
+BACK = 2
+LEFT = 3
+UP = 4
+DOWN = 5
+
+class Cube2(gym.Env):
+    def __init__(self):
+        super().__init__()
+        self.action_space = gym.spaces.Discrete(6)
+        self.observation_space = gym.spaces.Box(low=0, high=1, shape=(24, 6))
+        self.state = np.zeros((6, 2, 2))
+    
+    def reset(self, seed=None, options=None):
+        super().reset(seed=seed, options=options)
+        self.state = np.zeros((6, 2, 2))
+        self.state[0] = np.ones((2, 2)) * FRONT
+        self.state[1] = np.ones((2, 2)) * RIGHT
+        self.state[2] = np.ones((2, 2)) * BACK
+        self.state[3] = np.ones((2, 2)) * LEFT 
+        self.state[4] = np.ones((2, 2)) * UP
+        self.state[5] = np.ones((2, 2)) * DOWN
+        return self.state, {}
+    
+    def step(self, action):
+        new_state = self.state.copy()
+
+        # Front Clockwise
+        if action == 0:
+            # Up becomes right
+            new_state[RIGHT, 0, 0] = self.state[UP, 0, 0]
+            new_state[RIGHT, 1, 0] = self.state[UP, 1, 0]
+            # Right becomes down
+            new_state[DOWN, 0, 1] = self.state[RIGHT, 1, 0]
+            new_state[DOWN, 1, 1] = self.state[RIGHT, 0, 0]
+            # Down becomes left
+            new_state[LEFT, 0, 1] = self.state[DOWN, 0, 1]
+            new_state[LEFT, 1, 1] = self.state[DOWN, 1, 1]
+            # Left becomes up
+            new_state[UP, 0, 0] = self.state[LEFT, 1, 1]
+            new_state[UP, 1, 0] = self.state[LEFT, 0, 1]
+        # Front Counter-Clockwise
+        if action == 1:
+            # Up becomes left
+            new_state[LEFT, 0, 1] = self.state[UP, 1, 0]
+            new_state[LEFT, 1, 1] = self.state[UP, 0, 0]
+            # Left becomes down
+            new_state[DOWN, 0, 1] = self.state[LEFT, 0, 1]
+            new_state[DOWN, 1, 1] = self.state[LEFT, 1, 1]
+            # Down becomes right
+            new_state[RIGHT, 0, 0] = self.state[DOWN, 1, 1]
+            new_state[RIGHT, 1, 0] = self.state[DOWN, 0, 1]
+            # Right becomes up
+            new_state[UP, 0, 0] = self.state[RIGHT, 0, 0]
+            new_state[UP, 1, 0] = self.state[RIGHT, 1, 0]
+
+        self.state = new_state
+        return self.state, 0, False, False, {}

rlcube/uv.lock

@@ -697,12 +697,14 @@ version = "0.1.0"
 source = { virtual = "." }
 dependencies = [
     { name = "gymnasium" },
+    { name = "numpy" },
     { name = "stable-baselines3" },
 ]
 
 [package.metadata]
 requires-dist = [
     { name = "gymnasium", specifier = ">=1.2.0" },
+    { name = "numpy", specifier = ">=2.3.2" },
     { name = "stable-baselines3", specifier = ">=2.7.0" },
 ]